Triple

T24001114

Position	Surface form	Disambiguated ID	Type / Status
Subject	مصرف لبنان	`E594249`	entity
Predicate	يرتبط_مع	`P37`	FINISHED
Object	وزارة المالية اللبنانية وزارة المالية اللبنانية هي الجهة الحكومية المسؤولة عن إعداد وتنفيذ السياسة المالية للدولة اللبنانية، بما يشمل إعداد الموازنة العامة وإدارة الإيرادات والإنفاق العام والدين العام.	`E1614774`	NE FINISHED

How this triple was built (3 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini

Instruction

Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).

Input

Phrase: وزارة المالية اللبنانية | Statement: [مصرف لبنان, يرتبط_مع, وزارة المالية اللبنانية]

NEDg Description generation gpt-5.1

Instruction

Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"

Input

Entity: وزارة المالية اللبنانية
Triple: [مصرف لبنان, يرتبط_مع, وزارة المالية اللبنانية]

Generated description

وزارة المالية اللبنانية هي الجهة الحكومية المسؤولة عن إعداد وتنفيذ السياسة المالية للدولة اللبنانية، بما يشمل إعداد الموازنة العامة وإدارة الإيرادات والإنفاق العام والدين العام.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: يرتبط_مع
Context triple: [مصرف لبنان, يرتبط_مع, وزارة المالية اللبنانية]

A. повʼязанеЗ
Indicates a general association or connection between one entity and another.
B. relatedPass
Indicates that one pass is associated with or connected to another pass in some relevant way.
C. relatesComplementTo
Indicates that one entity serves as a complement or completing counterpart to another entity within a specified context or structure.
D. relatedTo chosen
Indicates a general, non-specific relationship or association exists between two entities.
E. مرتبطب
Indicates a relationship of being connected, associated, or related to something or someone.
F. None of above.

Provenance (6 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step	Stage	Batch ID	Status	When
creating	Elicitation	`batch_69e288b9ecf08190b8c94a278f5674fe`	completed	April 17, 2026, 7:23 p.m.
NER	Named-entity recognition	`batch_69f1d464f1988190a0a9352c1ec214eb`	completed	April 29, 2026, 9:50 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a0f7e969554819087c6237d2e5f75cf`	completed	May 21, 2026, 9:52 p.m.
NEDg	Description generation	`batch_6a0f7f4da3048190af7ef06dcec0a651`	completed	May 21, 2026, 9:55 p.m.
NED2	Entity disambiguation (via description)	`batch_6a0f801bcc9c81908bbb270d7e762c11`	completed	May 21, 2026, 9:58 p.m.
PD	Predicate disambiguation	`batch_69f1615994c48190a5de95d3f7e5cd0a`	completed	April 29, 2026, 1:39 a.m.

Created at: April 17, 2026, 9:39 p.m.